Correlated Drug Terms (0)

---

	Name (Synonyms)	Correlation

Correlated MeSH Terms (1)

---

	Name (Synonyms)	Correlation
D055370	Lung Injury NIH	0.21

Correlated HPO Terms (0)

---

	Name (Synonyms)	Correlation

Primary Outcomes

Description: Describe the parenchymal lung damage induced by COVID-19 through a qualitative analysis with chest CT through artificial intelligence techniques.

Measure: A qualitative analysis of parenchymal lung damage induced by COVID-19

Time: Until patient discharge from the hospital (approximately 6 months)

---

Description: Describe the parenchymal lung damage induced by COVID-19 through a quantitative analysis with chest CT through artificial intelligence techniques.

Measure: A quantitative analysis of parenchymal lung damage induced by COVID-19

Time: Until patient discharge from the hospital (approximately 6 months)

---

Secondary Outcomes

Description: The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure assessed as intensive care mortality.

Measure: The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure.

Time: Until patient discharge from the hospital (approximately 6 months)

---

Description: The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure assessed as hospital mortality.

Measure: The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure.

Time: Until patient discharge from the hospital (approximately 6 months)

---

Description: The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure assessed as days free from mechanical ventilation.

Measure: The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure.

Time: Until patient discharge from the hospital (approximately 6 months)

---

Description: The hypothesis is that the uso of deep neural network models for lung segmentation in Acute Respiratory Distress Syndrome (ARDS) in animal models and Chronic Obstructive Pulmonary Disease (COPD) in patients that could be applied to self-segment the lungs of COVID-19 patients through a learning transfer mechanism with artificial intelligence.

Measure: Automated segmentation of lung scans of patients with COVID-19 and ARDS.

Time: Until patient discharge from the hospital (approximately 6 months)

---

Description: Expand the knowledge of chest CT features in COVID-19 patients and their detail through the use of machine learning and other quantitative techniques comparing CT patterns of COVID-19 patients to those of patients with ARDS.

Measure: Knowledge of chest CT features in COVID-19 patients and their detail through the use of machine learning and other quantitative techniques.

Time: Until patient discharge from the hospital (approximately 6 months)

---

Description: Determine the capacity within which the artificial intelligence analysis that uses deep learning models can be used to predict clinical outcomes from the analysis of the characteristics of the chest CT obtained within 7 days of hospital admission; combining quantitative CT data with clinical data.

Measure: The ability within which the analysis of artificial intelligence that uses deep learning models can be used to predict clinical outcomes

Time: Until patient discharge from the hospital (approximately 6 months)

---